Character voice communication system
Radio telephone system having recording and reproduction functions
Both way recording method of a wireless telephone
Portable documentation system
Digital radio telephone apparatus having automatic answering/recording functions
Portable telephone set incorporating a message recording feature
Voice mail telephone answering device
Conversion of communicated speech to text for tranmission as RF modulated base band video
Messaging system scratchpad facility
Mobile telephone having continuous recording capability
ApplicationNo. 10260636 filed on 09/27/2002
US Classes:455/550.1, Radiotelephone equipment detail455/412.1, Message storage or retrieval455/419, Remote programming control455/566, Having display704/271, Handicap aid379/88.08, Message signal analysis704/276, Pattern display379/88.01, Voice activation or recognition704/260, Image to speech704/235, Speech to image379/88.22, Message management379/88.13, Multimedia system (e.g., voice output combined with fax, video, text, etc.)370/401, Bridge or gateway between networks379/88.17, Interaction with an external nontelephone network (e.g., Internet)455/563Having voice recognition or synthesization
ExaminersPrimary: Gesesse, Tilahun
Assistant: Lee, John D.
Attorney, Agent or Firm
International ClassesH04B 1/38
CROSS-REFERENCE TO RELATED APPLICATIONS
This application is related to the following applications, which have common inventorship and are assigned to the same assignee as the present application and are hereby incorporated herein by reference:
METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR AUTHORIZING RE-RECORDING, filed Jun. 26, 2002 application Ser. No. 10/183,860; and
METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR AUTHORIZING RECORDING OF A MESSAGE, filed Jun. 26, 2002, application Ser. No. 10/183,792.
1. Field of the Invention
This invention concerns transcribing spoken communication, and more particularly concerns transcribing a telephone communication.
2. Related Art
In recent years there has been tremendous growth in telecommunications technology. Even though cell phone high-speed data services are only just beginning, there are reportedly already 130 million cell phones in use in the United States as ofmid-2002. The Cellular Telecommunications and Internet Association, a trade group, reports that in the year 2002 billable cell phone calling will exceed half a trillion minutes. Due to the nature of their use, it is particularly useful to include incell phones message handling functionality. Another message handling telecommunications technology, voicemail, predates the mass proliferation of cell phones, but the use of voicemail continues to rapidly increase. Despite the spread of cell phones andvoicemail, there has not been a correspondingly great increase in user aids for managing these two telecommunications technologies. Consequently, a need exists for improving that management.
The foregoing need is addressed in the present invention. According to an apparatus form of the invention, an apparatus of a size and weight that is suitable to be carried easily in a pocket or purse includes telecommunications circuitryoperable to wirelessly send and receive voice communications directly to and from a cell phone network. The apparatus also has a processor communicatively coupled to the telecommunications circuitry for receiving the voice communications. A memory ofthe apparatus has program instructions for speech recognition stored therein and the processor is operable under control of the speech recognition program instructions to generate a transcript of the voice communications. The apparatus also includes adisplay and the memory has program instructions for a display function stored therein. The processor is operable under control of the display program instructions to project the transcript on the display.
In another aspect, the memory has program instructions for a transfer function and wherein the processor is operable under control of the transfer function program instructions to transfer the transcript for printing.
In a still further aspect, the memory has program instructions for a utility function stored therein, and the processor is operable under control of the utility program instructions to store a data structure for the transcript in the memory.
In yet another aspect, the processor is operable under control of the utility program instructions to store a data structure for the voice communications in the memory.
In another aspect, the memory has program instructions for an editing function stored therein, and the processor is operable under control of the editing program instructions to automatically selectively extract information from the transcript.
Objects, advantages, additional aspects and other forms of the invention will become apparent upon reading the following detailed description and upon reference to the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 illustrates certain functions and information flow for the present invention, according to an embodiment.
FIG. 2 illustrates structure of an apparatus of the present invention, according to an embodiment.
FIG. 3 illustrates an algorithm for the present invention in flow chart form, according to an embodiment.
DETAILED DESCRIPTION OF A PREFERRED EMBODIMENT
The claims at the end of this application set out novel features which applicants believe are characteristic of the invention. The invention, a preferred mode of use, further objectives and advantages, will best be understood by reference to thefollowing detailed description of an illustrative embodiment read in conjunction with the accompanying drawings.
Referring first to FIG. 2, an apparatus 210 is shown, according to an embodiment of the present invention. The apparatus 210 is of a size and weight that is suitable to be carried easily in a pocket or purse. For example, in an embodiment theapparatus 210 is less than 7×4×1 inch in size and weighs less than 8 ounces. In contrast to a household telephone, the apparatus 210 includes telecommunications circuitry 250 operable to wirelessly send and receive voice communicationsdirectly to and from a cell phone network, for example, the Verizon Wireless or Sprint PCS networks. That is, the telecommunications circuitry 250 communications wirelessly directly to a cell tower, for example, rather than through wires that atelephone service provider typically installs for home telephone service.
The apparatus 210 also includes a processor 215, a memory 220, which includes a volatile memory 225 (that is, random access memory, for example) and a nonvolatile memory 230 (for example, read only memory, hard disk, floppy disk, CD-ROM, etc.). The memory 220 is for storing a program or programs 237 for controlling the processor 215 and for storing data 238, described further herein below. Processor 215 is operative with the programs 237 to perform functions as described herein. The apparatus210 also has a display 205 which receives a display signal from a display adapter 241.
The display 205 includes a touch-sensitive screen for receiving input from a stylus manipulated by a user. In this embodiment the system 210 also has keys 235, i.e., a keypad, buttons etc., which compose a collection of the sort that issometimes referred to as a "data entry device." The system 210 also includes a microphone 245 for receiving voice commands. In other embodiments, the system 210 includes other data entry devices, and may or may not omit the keys 235, microphone 245,etc.
The components in the system 210 are generally interconnected by bus 240. Some of the components are connected to the bus 240 by adapters. The adapter 241 for display 205 has already been mentioned. Keys 235, microphone 245 and telecomcircuitry 250 also are coupled to the bus 240 via respective adapters 242, 247 and 243. This interconnection of components permits them to communicate with one another. For example, the processor is communicatively coupled to the telecommunicationscircuitry 250 by means of the bus 240 and adapter 243 so that the processor 215 can receive voice communications 260 via the telecommunications circuitry 250. An input/output ("I/O") adapter 244 is also coupled to the bus 240 to enable transferringinformation among components of the apparatus 210 and external devices (not shown).
Apparatus 210 takes various configurations in different embodiments, each of which may generally be referred to as a "computer system." For example, in various embodiments the computer system may include a personal digital assistant ("PDA"),conventional telephone, cell phone, appliance with embedded processor and memory, etc. That is, it should be understood that the term "computer system" is intended to encompass any device having a processor that executes instructions from a memorymedium.
The memory 220 preferably stores instructions (also known as a "software program" or simply "program") for implementing various embodiments of a method in accordance with the present invention. In various embodiments the one or more softwareprograms are implemented in various ways, including procedure-based techniques, component-based techniques, and/or object-oriented techniques, among others. Specific examples include XML, C objects, Java and Microsoft Foundation Classes (MFC).
Referring now to FIG. 1, additional aspects, particularly functional aspects, of the present invention are illustrated, according to an embodiment. (Elements shown herein in more than one figure generally have like element numbers throughout.)The processor 215 (FIG. 2) receives voice communication 160 from the telecommunications circuitry 250 (FIG. 2). The voice communication 160 includes data that essentially reproduces, in a digital format, audio information from a spoken communication 260(FIG. 2) received by telecommunictions circuitry 250. The processor 215 processes voice communication 160, under the control of a speech recognition function 110 portion of instructions for one or more programs 237, to generate a raw transcript 112 ofthe communication 160. The raw transcript 112 is text-based digital information, such as in the form of the well-known ASCII text.
Transcript 112 is in turn processed, under control of a utility function 115 portion of the instructions, to generate and save in memory 220 a data structure 117 for the transcript 112. Likewise, the voice communication 160 is processed,controlled by the utility function 115, to generate and save in memory 220 a data structure 119 for the voice communication 160. These data structures 117 and 119 are examples of data 238 shown in FIG. 1, and are formatted so as to be compatible withsome other computer program function or external device.
The processor 215 is operable to transfer the data structures 117 and 119 externally via the I/O adapter 244 (FIG. 2) under control of a transfer function 140 portion of instructions for the program(s) 237. In the embodiment, the user may formatthe transcript data structure 117 for printing and may accordingly send the data structure 117 to an external printer 172 which prints the transcript 117. The user may also format the transcript data structure 117 in a format compatible with a wordprocessing application and transfer it such as by sending the data structure 117 via the Internet, for example, by attaching it or otherwise associating it with an e-mail message, or uploading it to a storage area on a web site. The data structure 117may also be transferred by other means, such as by infra-red beam, USB cable, etc. to some other computer system. The user may likewise format the voice communication data structure 119 in a standard format such as that of a ".wav" file compatible witha playback device, and likewise transfer it by sending the data structure 119 via the Internet or some other means.
Likewise, the voice communication 160 is processed, controlled by the utility function 115, to generate a derivative voice communication 162 which is transferred as an audio transmission to another telecommunications device via thetelecommunications circuitry 250. This includes sending the voice communication 162 to a voice mail system, as described in the above cross referenced, related applications.
Convenience in transfer of data structure 117, data structure 119 or derivative voice communication 162 is enabled by commands invoked by predefined keys 235 (FIG. 2) or combinations of keys 235, selectable icons displayed on touch sensitivedisplay 205 (FIG. 2) or predefined spoken words received by microphone 245 (FIG. 2) and recognized by speech recognition function 110.
Note that the user may select only pieces of the voice communication 160 to process and save as a transcript 112, derivative voice communication 162, transcript data structure 117, or voice communication data structure 119.
The processor 215 also processes the raw transcript 112 under control of a display function 120 portion of instructions for the program(s) 237 and responsively projects on the display 205 (FIG. 2) the transcript 112, as projected transcript 122. (As elsewhere herein, the processor 215 may process the transcript data structure 117 instead of the raw transcript 112.)
Either before or after before the transcript 112 is generated the user of the apparatus 210 may specify categories of information to be automatically recognized and extracted from the transcript 112. (In alternative embodiments, the voicecommunication 105 or voice communication data structure 119 is the source material processed instead of the transcript 112 or data structure 117, under control of the speech recognition function 110, for recognition and extraction.) The categories ofinformation specified include names, phone numbers, postal addresses, e-mail addresses, URL's, etc. The user is not limited to specifying categories of information to be recognized and extracted, but may also specify very specific information. Forexample, the user may specify extraction of a certain name, number, word, group of names, numbers, words, or combinations thereof or text within a certain range of occurrence thereof. The raw transcript 112 (or data structure 117) is accordinglyprocessed, controlled by a first editing function 131 portion of the instructions, to responsively recognize and extract the specified information, thereby generating extracted information 135.
The user may also specify information to be extracted interactively. That is, the user may highlight on display 205 (FIG. 2) information shown as projected transcript 122, using a stylus on the touch sensitive screen or keys, and direct theediting function 135 to extract and save the selected information.
The processor 215 processes the extracted information 135, under the control of a second editing function 132 portion of instructions for the program(s) 237, to generate formatted information 137, which is a structured version of the extractedinformation 135 that is formatted to be compatible with an organizer function 150 or some external function or device. The processor 215 is operable to transfer the information 137 via I/O adapter 244 (FIG. 2), controlled by the previously mentionedtransfer function 140.
Under control of the organizer function 150 portion of instructions for the program(s) 237, the processor 215 processes organizer data 155, which generally includes data such as names, addresses, lists of things to do, notes, calendar relatedinformation, etc. that has been input by a user and stored in memory 220 (FIG. 2). Responsive to the organizer function 150 processing, the data 155 is merged with the formatted information 137 arising from the voice communication 260. This producesmerged organizer data 156, which includes structured information organized according to function in sections including address book, "to do" list, notepad, calendar, etc. The processor 215 processes the merged organizer data 156, controlled by thepreviously mentioned display function 120, and responsively projects the data 156 as projected merged organizer data 158 on the display 205 (FIG. 2). That is, the user may select from all the merged organizer data 156 any portion to be displayed asprojected merged organizer data 158.
Referring now to FIG. 3, a flow chart 300 is shown which illustrates method aspects of the invention more generally, according to an embodiment. It should be understood that the actions in the flow chart 300 do not necessarily have to beperformed in the particular sequence in which they are set out. The method begins at block 305, and then at 310 telecommunications circuitry of the apparatus receives a voice communication from a cell phone network. As previously indicated, a processoris communicatively coupled to the telecommunications circuitry. Next, at 315 the voice communication is received by a processor of the apparatus. At 320 a data structure for the voice communications is stored by the processor in the memory. Then, at325 a transcript of the voice communications is generated by the processor under control of speech recognition program instructions stored in a memory of the apparatus. At 330 a data structure for the transcript is stored by the processor in the memory.
At 335 the transcript is projected on a display of the apparatus responsive to processing the transcript by the processor. Next, at 340 information is extracted from the transcript by the processor. This may be in response to a user selectionof the information. That is, for example, the processor receives a selection indicated by the user on the display-projected transcript. Alternatively, the information may be extracted from the transcript automatically by the processor in response to aspecification entered by the user, typically, although not necessarily, before the transcript is even generated.
Next, at 345 the extracted information is formatted, such as to generate a data structure for the information conforming to a required format for an organizer application that may run on the same processor, or to conform to a format for someother application or device, which may or may not be external to the apparatus. At 350 the formatted, extracted information is merged with organizer data. At 355 the information is transferred to another device or application. As previously describedin connection with FIG. 1, this tranferring may include transferring a formated version of the transcript or excerpts therefrom to a printer for printing, transferring the transcript or excerpts therefrom as a data structure such as in a text file orword processing file format attached to an e-mail, uploaded to a web site, beamed to another device, etc., transferring an audio file of the voice communication or excerpts therefrom, etc.
The description of the present embodiment has been presented for purposes of illustration, but is not intended to be exhaustive or to limit the invention to the form disclosed. Many modifications and variations will be apparent to those ofordinary skill in the art. For example, those of ordinary skill in the art will appreciate that processes of the present invention are capable of being performed by a processor responsive to stored instructions, and accordingly some or all of theprocesses may be distributed in the form of a computer readable medium of instructions in a variety of forms and that the present invention applies equally regardless of the particular type of signal bearing media actually used to carry out thedistribution. Examples of computer readable media include RAM, flash memory, recordable-type media, such a floppy disk, a hard disk drive, a ROM, and CD-ROM, and transmission-type media such as digital and analog communications links, e.g., theInternet.
It should be understood, of course, that the functions and data structures shown in FIG. 1 are generated and parsed in different ways in different embodiments. For example, the raw transcript 112 and the transcript data structure 117 are one andthe same in another embodiment. Also, for example, the transcript data structure 117 is generated responsive to the speech recognition function 110 instructions rather than separate utility function 115 instructions in another embodiment.
From the above it should be appreciated that the telecommunications/transcription combination of the present invention reduces the need for the user to try and write with pen and paper while talking on the phone. The invention alsoadvantageously provides the capability to easily capture portions of voice communication, convert them from an audio format to a text-based format, and transfer them into any selected section of the organizer data 156 or to an external device with only afew keystrokes, button presses or stylus taps. Moreover, if the user specifies in advance the information to be captured, the information may even be captured and transferred automatically, with no further user intervention at all.
Increased accuracy as compared to the conventional pen-and-paper-while-talking approach is another advantage of the automatic transcription and selective data capture enabled by the invention. This leads to significant cost savings through errorreduction. Manually mis-transcribing a digit in a contract number, for example, can lead to incorrect billing and consequent delays in receiving payment.
To reiterate, the embodiments were chosen and described in order to best explain the principles of the invention, the practical application, and to enable others of ordinary skill in the art to understand the invention. Various other embodimentshaving various modifications may be suited to a particular use contemplated, but may be within the scope of the present invention. Moreover, it should be understood that the actions in the following claims do not necessarily have to be performed in theparticular sequence in which they are set out.
* * * * *
Field of SearchHaving voice recognition or synthesization
Message storage or retrieval
Having message notification
Format conversion (e.g., text, audio, etc.)
Remote programming control
Integrated with other device
Auxiliary data signaling (e.g., short message service (SMS))
Auto-dialing or repertory dialing (e.g., using bar code, etc.)
Personal digitial assistant
Interface attached device (e.g., interface with modem, facsimile, computer, etc.)
Radiotelephone equipment detail
Having particular application (e.g., avalanche victim assistance) of a transceiver